检索结果-内蒙古大学图书馆

algorithms, computing and data processing (acdp), international conference on

作者： Shiwei Gao Zhiwei Chen Xiaochao Dang Xiaohui Dong Wenfeng Zhao School of Computer Science And Engineering Northwest Normal University Lanzhou China

How to apply effective data augmentation methods to supplement datasets in harsh industrial environments is an important problem in complex industrial process modeling. In response to this problem, this paper proposes a new industrial process data augmentation method, DMM-WGAN, based on WGAN. Firstly, a Deep Threshold Mixing Feature Extraction Module (DMM) is proposed in the generator, which adopts a dual-channel fusion strategy. one channel extracts deep features of industrial data, while the other channel extracts global features of industrial data to enhance the feature extraction ability of the generator. Then, the DMM module and the Wasserstein Generative Adversarial Network are combined to establish the DMM-WGAN generation model. Finally, the proposed model is optimized and extensively experimented on a thermal power plant dataset, and the results are evaluated based on MSE, RMSE, MAE, and R2. The results show that the proposed DMM-WGAN generation model is superior to traditional VAE, GAN and WGAN generation models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Distributed Algorithm for IDC Snapshot data

A Distributed Algorithm for IDC Snapshot Data

引用

2023 international conference on Mobile Internet, Cloud computing and Information Security, MICCIS 2023

作者： Sun, Zhichao Meng, Weiye Wei, Sen China Telecom Research Institute AI Research Centre Beijing China

ISBN: (纸本)9798350300932

With the AI technology used in IDC energy saving, The whole room snapshot data are used in some scenarios, The room snapshot data is composed of the snapshot data of various devices in the room. These devices can only collect data regularly at a certain frequency due to settings, performance and other reasons, and can not achieve time synchronization and when used in AI algorithm the value from different collect time will cause inaccurate. Therefore, in the data processing and modeling phase, it is necessary to predict the device snapshot value at certain time, in practice , AI needs a large amount of training data to get good training results, and China Telecom has a large number of computer rooms that provide a large amount of training data. Generally, interpolation algorithms are used to unify data from multiple data sources, but data processing is only one step in the AI computing process. Traditional stand-Alone interpolation algorithms cannot meet the time requirements. This paper proposes a Spark based distributed interpolation algorithm, Experiments show that this algorithm can reduce the running time of the algorithm in equal proportion by increasing resources. © 2023 IEEE.

关键词： Energy conservation

来源：评论

学校读者我要写书评

暂无评论

Ensemble Learning Models for Large-Scale Time Series Forecasting in Supply Chain 22

Ensemble Learning Models for Large-Scale Time Series Forecas...

引用

IEEE 22nd international conference on Trust, Security and Privacy in computing and Communications (TrustCom) / BigdataSE conference / CSE conference / EUC conference / ISCI conference

作者： Zhang, Minjuan Wu, Chase Q. Hou, Aiqin New Jersey Inst Technol Dept Data Sci Newark NJ 07102 USA Northwest Univ Sch Informat Sci & Technol Xian 710127 Shaanxi Peoples R China

ISBN: (纸本)9798350381993;9798350382006

Machine learning techniques have gained significant traction in supply chain forecasting, driven by the increasing availability of data assets. These techniques offer opportunities to optimize management processes, reduce operational costs, and enhance decision-making for enterprise success. However, conventional statistical approaches dominating time series forecasting, such as the Autoregressive-moving-average model (ARMA), dynamic regression, and unobserved component models (UCMs), suffer from limitations in model accuracy and performance. They struggle to handle batch processing, large-scale big data, uncertainty-induced disruptions, and the synchronization of demand and supply scenarios. To address these challenges, we propose a class of ensemble techniques that combine neural networks with baseline models. Firstly, we conduct classification and segmentation by leveraging feature engineering on signal components, such as spikes and anomalies as outlier skews, to capture the complexity of combined scenarios in categorical data hierarchies and identify patterns for ensemble forecasting. Subsequently, we employ an ensemble model equipped with time series pattern sensors to automatically discern signal components, encompassing seasonality, promotions, trends, and intermittent or discontinued activities. We evaluate the performance of eight commonly-used model categories, and our proposed ensemble modeling approaches exhibit substantial improvements in accuracy compared to individual baseline models and other univariate time series algorithms.

关键词： Ensemble models time series forecasting large-scale data supply chain neural networks stacking techniques

来源：评论

学校读者我要写书评

暂无评论

A Study of Challenges and Limitations to Applying Machine Learning to Highly Unstructured data 7

A Study of Challenges and Limitations to Applying Machine Le...

引用

2023 7th international conference On computing, Communication, Control And Automation, ICCUBEA 2023

作者： Singh, Sahib Hooda, Susheela Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9798350304268

In recent years, there has been a lot of curiosity about the use of machine learning algorithms to analyze unstructured data, including social media posts and videos. The limitations and difficulties posed by these technologies must be overcome in order to guarantee accurate and trustworthy results, despite the promise they hold. This study examines the restrictions and difficulties associated with using machine learning algorithms on unstructured data. We identify the main difficulties in working with unstructured data, such as the lack of standardization and the difficulty in handling noise and bias, through a literature review and case studies. We then look at methods for overcoming these obstacles, such as feature engineering, pre-processing techniques, and ensemble methods. The results of this study have implications for both theoretical and applied work in machine learning, particularly in the fields of feature engineering, model selection, and data cleaning. This paper's goal is to provide a thorough understanding of the constraints and difficulties associated with using machine learning algorithms on unstructured data, as well as to contribute to the creation of best practices for handling these data type © 2023 IEEE.

关键词： Deep Learning Machine Learning Natural Language processing (NLP) Sentiment Analysis Social Media Posts Text classification Unstructured data

来源：评论

学校读者我要写书评

暂无评论

Research on the Design and Application of House Price Prediction algorithms and Model Based on Machine Learning

Research on the Design and Application of House Price Predic...

引用

2023 international conference on Internet of Things, Robotics and Distributed computing, ICIRDC 2023

作者： Chen, Kexin Huang, Jianhui International School Beijing University of Posts and Telecommunications Beijing China Institute of Computing Technology Chinese Academy Beijing China

ISBN: (纸本)9798350375275

With the development of the socio-economy, the real estate industry has grown rapidly worldwide. Housing prices, as an important indicator for measuring a city's economic development level, have significant impacts on people's lives, work, investments, and other aspects. Therefore, how to accurately predict housing prices has become a highly researched area of interest. In recent years, the continuous development and application of machine learning technology have provided new solutions for predicting housing prices. This article aims to study the data processing flow for housing price prediction. Through comparing and analyzing different algorithms, we will derive the optimal data processing flow and housing price prediction model, validate its prediction accuracy and stability, provide a reliable tool for the real estate industry, help make more scientific and precise decisions, and promote the continuous development of the industry. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

DSN: A DDPG-Based Scheduling Framework for Optimal Task Allocation in Cloud data Centers 2

DSN: A DDPG-Based Scheduling Framework for Optimal Task Allo...

引用

2nd international conference on Cloud computing, Big data Application and Software Engineering, CBASE 2023

作者： Huang, Qiang Liu, Hu Zhai, Xiangping Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing211106 China

ISBN: (纸本)9798350331448

In modern cloud data center environments, precise and efficient scheduling of data processing jobs emerges as paramount. While many production environments conventionally adopt heuristic strategies for scheduling batch processing jobs, these methods may fall short of achieving optimal scheduling in the face of complex environments or specialized tasks, thereby significantly extending the completion time of jobs. To address this issue, we introduce the DSN (Deep-Schedule-Net) framework - a cluster batch processing job scheduling method based on the DDPG algorithm and tailored to address task scheduling optimization problems under multi-resource constraints. Compared to other related algorithms, experimental results substantively affirm that the proposed algorithm markedly optimizes in curtailing batch task completion time. © 2023 IEEE.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

IoT data Confidentiality Self-Management

IoT Data Confidentiality Self-Management

引用

2023 IEEE international conference on Dependable, Autonomic and Secure computing, 2023 international conference on Pervasive Intelligence and computing, 2023 international conference on Cloud and Big data computing, 2023 international conference on Cyber Science and Technology Congress, DASC/PiCom/CBDCom/CyberSciTech 2023

作者： Garah, Abdelhamid Mbarek, Nader Kirgizov, Sergey University of Burgundy Lib Laboratory Dijon21000 France

ISBN: (纸本)9798350304602

As the number of connected devices increases, protecting sensitive information transmitted by IoT devices is critical. One of the most effective ways to ensure data confidentiality while accommodating the limited resources of constrained devices is to use lightweight cryptographic algorithms. However, managing these algorithms in IoT ecosystems is a significant challenge. To overcome this problem, we propose a new IoT framework that enables self-management of IoT data confidentiality based on the use of lightweight cryptography and the Autonomic computing paradigm. Our approach implements the MAPE-K closed control loop, which uses a decision tree algorithm to predict the most appropriate lightweight encryption algorithm based on the state of the IoT object, thus ensuring data confidentiality, improving system performance, and extending the lifetime of IoT devices. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Ant: An Efficient Lossless Compression Algorithm for IoT Time Series data 21

Ant: An Efficient Lossless Compression Algorithm for IoT Tim...

引用

21st IEEE international Symposium on Parallel and Distributed processing with Applications, 13th IEEE international conference on Big data and Cloud computing, 16th IEEE international conference on Social computing and Networking and 13th international conference on Sustainable computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Li, Junhui Xu, Guangping Yang, Hongzhang Wu, Yulei Tianjin University of Technology School of Computer Science and Engineering Tianjin China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin China Key Laboratory of Computer Vision and System Ministry of Education China University of Bristol Faculty of Science and Engineering Bristol United Kingdom

ISBN: (纸本)9798350329223

In various applications in Internet of Things like industrial monitoring, large amounts of floating-point time series data are generated at an unprecedented rate. Efficient compression algorithms can effectively reduce the size of data, enhance transmission performance and storage efficiency, and simultaneously lower storage costs. Therefore, there is a need for lightweight and efficient stream compression algorithms. In this paper, we propose a novel lossless floating-point data compression algorithm called Ant. The main idea is to encode double-precision floating-point numbers into integer form, calculate the delta between adjacent values, and then convert the delta into unsigned integers. This encoding method effectively reduces storage costs and improves data compression efficiency. Extensive experiments on real-world datasets demonstrate that our algorithm achieves compression speeds at least as fast as state-of-the-art streaming methods, and a 63% relative improvement in average compression rate. © 2023 IEEE.

关键词： Storage efficiency

来源：评论

学校读者我要写书评

暂无评论

Towards Reliable Collaborative data processing Ecosystems: Survey on data Quality Criteria 22

Towards Reliable Collaborative Data Processing Ecosystems: S...

引用

IEEE 22nd international conference on Trust, Security and Privacy in computing and Communications (TrustCom) / BigdataSE conference / CSE conference / EUC conference / ISCI conference

作者： Sahi, Louis Laborde, Romain Kandi, Mohamed-Ali Sibilla, Michelle Macilotti, Giorgia Abdelmalek, Benzekri Ferreira, Afonso Univ Toulouse III Paul Sabatier Inst Rech Informat Toulouse Toulouse France CNRS Inst Rech Informat Toulouse Toulouse France

ISBN: (纸本)9798350381993;9798350382006

data quality plays a crucial role in the data governance of organizations, as it is essential to ensure that data are fit for the purpose for which they are intended, whether for operational activities, decision-making processes, or strategic planning. As data silos begin to be integrated to form data spaces, guaranteeing data quality becomes a necessity to achieve a reliable collaborative ecosystem. Nevertheless, the concept of data quality remains ambiguous, with various definitions and interpretations offered in the literature, despite its importance. This lack of consensus has led to the need for a thorough review of the different data quality criteria used in scientific work. Therefore, this paper serves as a systematic survey aimed at exploring and consolidating diverse perspectives on data quality. By thoroughly analyzing existing literature, this study compiles a comprehensive set of 30 agreed-upon data quality criteria, with their respective names and definitions. These criteria act as a valuable resource for organizations seeking to establish effective data quality monitoring practices. Then, we expose challenges raised by collaborative data processing and highlight possible research directions where data quality plays a major role.

关键词： data quality data quality criteria trust reliability collaborative data processing decentralized data governance

来源：评论

学校读者我要写书评

暂无评论

GPU-Based algorithms for processing the k Nearest-Neighbor Query on Spatial data Using Partitioning and Concurrent Kernel Execution

引用

international JOURNAL OF PARALLEL PROGRAMMING 2023年第6期51卷 275-308页

作者： Velentzas, Polychronis Vassilakopoulos, Michael Corral, Antonio Antonopoulos, Christos Univ Thessaly Dept Elect & Comp Engn Sekeri & Cheiden Str Volos 38334 Greece Univ Almeria Dept Informat Carretera Sacramento La Canada de San Urbano s-n Almeria 04120 Spain

algorithms for answering the k nearest-neighbor (k-NN) query are widely used for queries in spatial databases and for distance classification of a group of query points against a reference dataset to derive the dominating feature class. GPU devices have significantly more processing cores than CPUs and faster device memory than the main memory accessed by CPUs, thus, providing higher computing power for processing demanding queries like the k-NN. However, since device and/or main memory may not be able to host an entire, rather big, reference and query datasets, storing these datasets in a fast secondary device, like a solid state disk (SSD), and partially retrieve the required, at each stage, partitions is, in many practical cases, a feasible solution. We propose and implement the first GPU-based algorithms for processing the k-NN query for big reference and query spatial data stored on SSDs. Based on 3d synthetic and real big spatial data, we experimentally compare these algorithms and highlight the most efficient algorithmic variation. This variation utilizes a CUDA feature known as Concurrent Kernel Execution, to further improve its performance.

关键词： k Nearest-neighbor query GPU SSD Spatial-queries algorithms Plane-sweep Parallel computing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：